The real question for AI is this: can we do reasoning and causality without symbol-manipulation? Deep learning founders like @YLeCun (see our debate) and Hinton (eg https://sites.google.com/site/krr2015/home/schedule …) have said no; I have argued yes.https://twitter.com/GaryMarcus/status/1065280340669816832 …
-
I have mentioned the NTM only as a proof of concept (symbolic operations in NN). I don't think anyone but individual cells use a TM design for practical computations.
i talk about universal function approximation vs symbol manipulation in chapter two of algebraic mind; too subtle for twitter, perhaps
-
-
If you don't want to buy a book you can also check out http://www.psych.nyu.edu/gary/marcusArticles/Marcus%202013%20treelets%20%5Bproofs%5D.pdf … if you haven't. There are advantages, disadvantages, tradeoffs between explitcitly vs implicitly symbolic, discrete vs continuous and search/sampling vs optimization. Lots of people don't acknowledge
-
And the idea that GOFAI ideas didn't lead anywhere is the biggest myth. Every database, verifier, WaveFunctionCollapse,symbolic algebra,type system, SMT is argument against it. In my case I could write yet another image analogy tool or I can write something that helps teach math
- 8 more replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.